diff --git a/html5lib/sanitizer.py b/html5lib/sanitizer.py
index 2cef2655..e7956578 100644
--- a/html5lib/sanitizer.py
+++ b/html5lib/sanitizer.py
@@ -25,141 +25,157 @@
class HTMLSanitizerMixin(object):
""" sanitization of XHTML+MathML+SVG and of inline style attributes."""
- acceptable_elements = ['a', 'abbr', 'acronym', 'address', 'area',
- 'article', 'aside', 'audio', 'b', 'big', 'blockquote', 'br', 'button',
- 'canvas', 'caption', 'center', 'cite', 'code', 'col', 'colgroup',
- 'command', 'datagrid', 'datalist', 'dd', 'del', 'details', 'dfn',
- 'dialog', 'dir', 'div', 'dl', 'dt', 'em', 'event-source', 'fieldset',
- 'figcaption', 'figure', 'footer', 'font', 'form', 'header', 'h1',
- 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'input', 'ins',
- 'keygen', 'kbd', 'label', 'legend', 'li', 'm', 'map', 'menu', 'meter',
- 'multicol', 'nav', 'nextid', 'ol', 'output', 'optgroup', 'option',
- 'p', 'pre', 'progress', 'q', 's', 'samp', 'section', 'select',
- 'small', 'sound', 'source', 'spacer', 'span', 'strike', 'strong',
- 'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'time', 'tfoot',
- 'th', 'thead', 'tr', 'tt', 'u', 'ul', 'var', 'video']
-
- mathml_elements = ['maction', 'math', 'merror', 'mfrac', 'mi',
- 'mmultiscripts', 'mn', 'mo', 'mover', 'mpadded', 'mphantom',
- 'mprescripts', 'mroot', 'mrow', 'mspace', 'msqrt', 'mstyle', 'msub',
- 'msubsup', 'msup', 'mtable', 'mtd', 'mtext', 'mtr', 'munder',
- 'munderover', 'none']
-
- svg_elements = ['a', 'animate', 'animateColor', 'animateMotion',
- 'animateTransform', 'clipPath', 'circle', 'defs', 'desc', 'ellipse',
- 'font-face', 'font-face-name', 'font-face-src', 'g', 'glyph', 'hkern',
- 'linearGradient', 'line', 'marker', 'metadata', 'missing-glyph',
- 'mpath', 'path', 'polygon', 'polyline', 'radialGradient', 'rect',
- 'set', 'stop', 'svg', 'switch', 'text', 'title', 'tspan', 'use']
-
- acceptable_attributes = ['abbr', 'accept', 'accept-charset', 'accesskey',
- 'action', 'align', 'alt', 'autocomplete', 'autofocus', 'axis',
- 'background', 'balance', 'bgcolor', 'bgproperties', 'border',
- 'bordercolor', 'bordercolordark', 'bordercolorlight', 'bottompadding',
- 'cellpadding', 'cellspacing', 'ch', 'challenge', 'char', 'charoff',
- 'choff', 'charset', 'checked', 'cite', 'class', 'clear', 'color',
- 'cols', 'colspan', 'compact', 'contenteditable', 'controls', 'coords',
- 'data', 'datafld', 'datapagesize', 'datasrc', 'datetime', 'default',
- 'delay', 'dir', 'disabled', 'draggable', 'dynsrc', 'enctype', 'end',
- 'face', 'for', 'form', 'frame', 'galleryimg', 'gutter', 'headers',
- 'height', 'hidefocus', 'hidden', 'high', 'href', 'hreflang', 'hspace',
- 'icon', 'id', 'inputmode', 'ismap', 'keytype', 'label', 'leftspacing',
- 'lang', 'list', 'longdesc', 'loop', 'loopcount', 'loopend',
- 'loopstart', 'low', 'lowsrc', 'max', 'maxlength', 'media', 'method',
- 'min', 'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'open',
- 'optimum', 'pattern', 'ping', 'point-size', 'poster', 'pqg', 'preload',
- 'prompt', 'radiogroup', 'readonly', 'rel', 'repeat-max', 'repeat-min',
- 'replace', 'required', 'rev', 'rightspacing', 'rows', 'rowspan',
- 'rules', 'scope', 'selected', 'shape', 'size', 'span', 'src', 'start',
- 'step', 'style', 'summary', 'suppress', 'tabindex', 'target',
- 'template', 'title', 'toppadding', 'type', 'unselectable', 'usemap',
- 'urn', 'valign', 'value', 'variable', 'volume', 'vspace', 'vrml',
- 'width', 'wrap', 'xml:lang']
-
- mathml_attributes = ['actiontype', 'align', 'columnalign', 'columnalign',
- 'columnalign', 'columnlines', 'columnspacing', 'columnspan', 'depth',
- 'display', 'displaystyle', 'equalcolumns', 'equalrows', 'fence',
- 'fontstyle', 'fontweight', 'frame', 'height', 'linethickness', 'lspace',
- 'mathbackground', 'mathcolor', 'mathvariant', 'mathvariant', 'maxsize',
- 'minsize', 'other', 'rowalign', 'rowalign', 'rowalign', 'rowlines',
- 'rowspacing', 'rowspan', 'rspace', 'scriptlevel', 'selection',
- 'separator', 'stretchy', 'width', 'width', 'xlink:href', 'xlink:show',
- 'xlink:type', 'xmlns', 'xmlns:xlink']
-
- svg_attributes = ['accent-height', 'accumulate', 'additive', 'alphabetic',
- 'arabic-form', 'ascent', 'attributeName', 'attributeType',
- 'baseProfile', 'bbox', 'begin', 'by', 'calcMode', 'cap-height',
- 'class', 'clip-path', 'color', 'color-rendering', 'content', 'cx',
- 'cy', 'd', 'dx', 'dy', 'descent', 'display', 'dur', 'end', 'fill',
- 'fill-opacity', 'fill-rule', 'font-family', 'font-size',
- 'font-stretch', 'font-style', 'font-variant', 'font-weight', 'from',
- 'fx', 'fy', 'g1', 'g2', 'glyph-name', 'gradientUnits', 'hanging',
- 'height', 'horiz-adv-x', 'horiz-origin-x', 'id', 'ideographic', 'k',
- 'keyPoints', 'keySplines', 'keyTimes', 'lang', 'marker-end',
- 'marker-mid', 'marker-start', 'markerHeight', 'markerUnits',
- 'markerWidth', 'mathematical', 'max', 'min', 'name', 'offset',
- 'opacity', 'orient', 'origin', 'overline-position',
- 'overline-thickness', 'panose-1', 'path', 'pathLength', 'points',
- 'preserveAspectRatio', 'r', 'refX', 'refY', 'repeatCount',
- 'repeatDur', 'requiredExtensions', 'requiredFeatures', 'restart',
- 'rotate', 'rx', 'ry', 'slope', 'stemh', 'stemv', 'stop-color',
- 'stop-opacity', 'strikethrough-position', 'strikethrough-thickness',
- 'stroke', 'stroke-dasharray', 'stroke-dashoffset', 'stroke-linecap',
- 'stroke-linejoin', 'stroke-miterlimit', 'stroke-opacity',
- 'stroke-width', 'systemLanguage', 'target', 'text-anchor', 'to',
- 'transform', 'type', 'u1', 'u2', 'underline-position',
- 'underline-thickness', 'unicode', 'unicode-range', 'units-per-em',
- 'values', 'version', 'viewBox', 'visibility', 'width', 'widths', 'x',
- 'x-height', 'x1', 'x2', 'xlink:actuate', 'xlink:arcrole',
- 'xlink:href', 'xlink:role', 'xlink:show', 'xlink:title', 'xlink:type',
- 'xml:base', 'xml:lang', 'xml:space', 'xmlns', 'xmlns:xlink', 'y',
- 'y1', 'y2', 'zoomAndPan']
-
- attr_val_is_uri = ['href', 'src', 'cite', 'action', 'longdesc', 'poster', 'background', 'datasrc',
- 'dynsrc', 'lowsrc', 'ping', 'poster', 'xlink:href', 'xml:base']
-
- svg_attr_val_allows_ref = ['clip-path', 'color-profile', 'cursor', 'fill',
- 'filter', 'marker', 'marker-start', 'marker-mid', 'marker-end',
- 'mask', 'stroke']
-
- svg_allow_local_href = ['altGlyph', 'animate', 'animateColor',
- 'animateMotion', 'animateTransform', 'cursor', 'feImage', 'filter',
- 'linearGradient', 'pattern', 'radialGradient', 'textpath', 'tref',
- 'set', 'use']
-
- acceptable_css_properties = ['azimuth', 'background-color',
- 'border-bottom-color', 'border-collapse', 'border-color',
- 'border-left-color', 'border-right-color', 'border-top-color', 'clear',
- 'color', 'cursor', 'direction', 'display', 'elevation', 'float', 'font',
- 'font-family', 'font-size', 'font-style', 'font-variant', 'font-weight',
- 'height', 'letter-spacing', 'line-height', 'overflow', 'pause',
- 'pause-after', 'pause-before', 'pitch', 'pitch-range', 'richness',
- 'speak', 'speak-header', 'speak-numeral', 'speak-punctuation',
- 'speech-rate', 'stress', 'text-align', 'text-decoration', 'text-indent',
- 'unicode-bidi', 'vertical-align', 'voice-family', 'volume',
- 'white-space', 'width']
-
- acceptable_css_keywords = ['auto', 'aqua', 'black', 'block', 'blue',
- 'bold', 'both', 'bottom', 'brown', 'center', 'collapse', 'dashed',
- 'dotted', 'fuchsia', 'gray', 'green', '!important', 'italic', 'left',
- 'lime', 'maroon', 'medium', 'none', 'navy', 'normal', 'nowrap', 'olive',
- 'pointer', 'purple', 'red', 'right', 'solid', 'silver', 'teal', 'top',
- 'transparent', 'underline', 'white', 'yellow']
-
- acceptable_svg_properties = ['fill', 'fill-opacity', 'fill-rule',
- 'stroke', 'stroke-width', 'stroke-linecap', 'stroke-linejoin',
- 'stroke-opacity']
-
- acceptable_protocols = ['ed2k', 'ftp', 'http', 'https', 'irc',
- 'mailto', 'news', 'gopher', 'nntp', 'telnet', 'webcal',
- 'xmpp', 'callto', 'feed', 'urn', 'aim', 'rsync', 'tag',
- 'ssh', 'sftp', 'rtsp', 'afs', 'data']
-
- acceptable_content_types = ['image/png', 'image/jpeg', 'image/gif', 'image/webp', 'image/bmp', 'text/plain']
+ acceptable_elements = frozenset((
+ 'a', 'abbr', 'acronym', 'address', 'area',
+ 'article', 'aside', 'audio', 'b', 'big', 'blockquote', 'br', 'button',
+ 'canvas', 'caption', 'center', 'cite', 'code', 'col', 'colgroup',
+ 'command', 'datagrid', 'datalist', 'dd', 'del', 'details', 'dfn',
+ 'dialog', 'dir', 'div', 'dl', 'dt', 'em', 'event-source', 'fieldset',
+ 'figcaption', 'figure', 'footer', 'font', 'form', 'header', 'h1',
+ 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'input', 'ins',
+ 'keygen', 'kbd', 'label', 'legend', 'li', 'm', 'map', 'menu', 'meter',
+ 'multicol', 'nav', 'nextid', 'ol', 'output', 'optgroup', 'option',
+ 'p', 'pre', 'progress', 'q', 's', 'samp', 'section', 'select',
+ 'small', 'sound', 'source', 'spacer', 'span', 'strike', 'strong',
+ 'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'time', 'tfoot',
+ 'th', 'thead', 'tr', 'tt', 'u', 'ul', 'var', 'video'))
+
+ mathml_elements = frozenset((
+ 'maction', 'math', 'merror', 'mfrac', 'mi',
+ 'mmultiscripts', 'mn', 'mo', 'mover', 'mpadded', 'mphantom',
+ 'mprescripts', 'mroot', 'mrow', 'mspace', 'msqrt', 'mstyle', 'msub',
+ 'msubsup', 'msup', 'mtable', 'mtd', 'mtext', 'mtr', 'munder',
+ 'munderover', 'none'))
+
+ svg_elements = frozenset((
+ 'a', 'animate', 'animateColor', 'animateMotion',
+ 'animateTransform', 'clipPath', 'circle', 'defs', 'desc', 'ellipse',
+ 'font-face', 'font-face-name', 'font-face-src', 'g', 'glyph', 'hkern',
+ 'linearGradient', 'line', 'marker', 'metadata', 'missing-glyph',
+ 'mpath', 'path', 'polygon', 'polyline', 'radialGradient', 'rect',
+ 'set', 'stop', 'svg', 'switch', 'text', 'title', 'tspan', 'use'))
+
+ acceptable_attributes = frozenset((
+ 'abbr', 'accept', 'accept-charset', 'accesskey',
+ 'action', 'align', 'alt', 'autocomplete', 'autofocus', 'axis',
+ 'background', 'balance', 'bgcolor', 'bgproperties', 'border',
+ 'bordercolor', 'bordercolordark', 'bordercolorlight', 'bottompadding',
+ 'cellpadding', 'cellspacing', 'ch', 'challenge', 'char', 'charoff',
+ 'choff', 'charset', 'checked', 'cite', 'class', 'clear', 'color',
+ 'cols', 'colspan', 'compact', 'contenteditable', 'controls', 'coords',
+ 'data', 'datafld', 'datapagesize', 'datasrc', 'datetime', 'default',
+ 'delay', 'dir', 'disabled', 'draggable', 'dynsrc', 'enctype', 'end',
+ 'face', 'for', 'form', 'frame', 'galleryimg', 'gutter', 'headers',
+ 'height', 'hidefocus', 'hidden', 'high', 'href', 'hreflang', 'hspace',
+ 'icon', 'id', 'inputmode', 'ismap', 'keytype', 'label', 'leftspacing',
+ 'lang', 'list', 'longdesc', 'loop', 'loopcount', 'loopend',
+ 'loopstart', 'low', 'lowsrc', 'max', 'maxlength', 'media', 'method',
+ 'min', 'multiple', 'name', 'nohref', 'noshade', 'nowrap', 'open',
+ 'optimum', 'pattern', 'ping', 'point-size', 'poster', 'pqg', 'preload',
+ 'prompt', 'radiogroup', 'readonly', 'rel', 'repeat-max', 'repeat-min',
+ 'replace', 'required', 'rev', 'rightspacing', 'rows', 'rowspan',
+ 'rules', 'scope', 'selected', 'shape', 'size', 'span', 'src', 'start',
+ 'step', 'style', 'summary', 'suppress', 'tabindex', 'target',
+ 'template', 'title', 'toppadding', 'type', 'unselectable', 'usemap',
+ 'urn', 'valign', 'value', 'variable', 'volume', 'vspace', 'vrml',
+ 'width', 'wrap', 'xml:lang'))
+
+ mathml_attributes = frozenset((
+ 'actiontype', 'align', 'columnalign', 'columnalign',
+ 'columnalign', 'columnlines', 'columnspacing', 'columnspan', 'depth',
+ 'display', 'displaystyle', 'equalcolumns', 'equalrows', 'fence',
+ 'fontstyle', 'fontweight', 'frame', 'height', 'linethickness', 'lspace',
+ 'mathbackground', 'mathcolor', 'mathvariant', 'mathvariant', 'maxsize',
+ 'minsize', 'other', 'rowalign', 'rowalign', 'rowalign', 'rowlines',
+ 'rowspacing', 'rowspan', 'rspace', 'scriptlevel', 'selection',
+ 'separator', 'stretchy', 'width', 'width', 'xlink:href', 'xlink:show',
+ 'xlink:type', 'xmlns', 'xmlns:xlink'))
+
+ svg_attributes = frozenset((
+ 'accent-height', 'accumulate', 'additive', 'alphabetic',
+ 'arabic-form', 'ascent', 'attributeName', 'attributeType',
+ 'baseProfile', 'bbox', 'begin', 'by', 'calcMode', 'cap-height',
+ 'class', 'clip-path', 'color', 'color-rendering', 'content', 'cx',
+ 'cy', 'd', 'dx', 'dy', 'descent', 'display', 'dur', 'end', 'fill',
+ 'fill-opacity', 'fill-rule', 'font-family', 'font-size',
+ 'font-stretch', 'font-style', 'font-variant', 'font-weight', 'from',
+ 'fx', 'fy', 'g1', 'g2', 'glyph-name', 'gradientUnits', 'hanging',
+ 'height', 'horiz-adv-x', 'horiz-origin-x', 'id', 'ideographic', 'k',
+ 'keyPoints', 'keySplines', 'keyTimes', 'lang', 'marker-end',
+ 'marker-mid', 'marker-start', 'markerHeight', 'markerUnits',
+ 'markerWidth', 'mathematical', 'max', 'min', 'name', 'offset',
+ 'opacity', 'orient', 'origin', 'overline-position',
+ 'overline-thickness', 'panose-1', 'path', 'pathLength', 'points',
+ 'preserveAspectRatio', 'r', 'refX', 'refY', 'repeatCount',
+ 'repeatDur', 'requiredExtensions', 'requiredFeatures', 'restart',
+ 'rotate', 'rx', 'ry', 'slope', 'stemh', 'stemv', 'stop-color',
+ 'stop-opacity', 'strikethrough-position', 'strikethrough-thickness',
+ 'stroke', 'stroke-dasharray', 'stroke-dashoffset', 'stroke-linecap',
+ 'stroke-linejoin', 'stroke-miterlimit', 'stroke-opacity',
+ 'stroke-width', 'systemLanguage', 'target', 'text-anchor', 'to',
+ 'transform', 'type', 'u1', 'u2', 'underline-position',
+ 'underline-thickness', 'unicode', 'unicode-range', 'units-per-em',
+ 'values', 'version', 'viewBox', 'visibility', 'width', 'widths', 'x',
+ 'x-height', 'x1', 'x2', 'xlink:actuate', 'xlink:arcrole',
+ 'xlink:href', 'xlink:role', 'xlink:show', 'xlink:title', 'xlink:type',
+ 'xml:base', 'xml:lang', 'xml:space', 'xmlns', 'xmlns:xlink', 'y',
+ 'y1', 'y2', 'zoomAndPan'))
+
+ attr_val_is_uri = frozenset((
+ 'href', 'src', 'cite', 'action', 'longdesc', 'poster', 'background',
+ 'datasrc', 'dynsrc', 'lowsrc', 'ping', 'poster', 'xlink:href',
+ 'xml:base'))
+
+ svg_attr_val_allows_ref = frozenset((
+ 'clip-path', 'color-profile', 'cursor', 'fill',
+ 'filter', 'marker', 'marker-start', 'marker-mid', 'marker-end',
+ 'mask', 'stroke'))
+
+ svg_allow_local_href = frozenset((
+ 'altGlyph', 'animate', 'animateColor',
+ 'animateMotion', 'animateTransform', 'cursor', 'feImage', 'filter',
+ 'linearGradient', 'pattern', 'radialGradient', 'textpath', 'tref',
+ 'set', 'use'))
+
+ acceptable_css_properties = frozenset((
+ 'azimuth', 'background-color',
+ 'border-bottom-color', 'border-collapse', 'border-color',
+ 'border-left-color', 'border-right-color', 'border-top-color', 'clear',
+ 'color', 'cursor', 'direction', 'display', 'elevation', 'float', 'font',
+ 'font-family', 'font-size', 'font-style', 'font-variant', 'font-weight',
+ 'height', 'letter-spacing', 'line-height', 'overflow', 'pause',
+ 'pause-after', 'pause-before', 'pitch', 'pitch-range', 'richness',
+ 'speak', 'speak-header', 'speak-numeral', 'speak-punctuation',
+ 'speech-rate', 'stress', 'text-align', 'text-decoration', 'text-indent',
+ 'unicode-bidi', 'vertical-align', 'voice-family', 'volume',
+ 'white-space', 'width'))
+
+ acceptable_css_keywords = frozenset((
+ 'auto', 'aqua', 'black', 'block', 'blue',
+ 'bold', 'both', 'bottom', 'brown', 'center', 'collapse', 'dashed',
+ 'dotted', 'fuchsia', 'gray', 'green', '!important', 'italic', 'left',
+ 'lime', 'maroon', 'medium', 'none', 'navy', 'normal', 'nowrap', 'olive',
+ 'pointer', 'purple', 'red', 'right', 'solid', 'silver', 'teal', 'top',
+ 'transparent', 'underline', 'white', 'yellow'))
+
+ acceptable_svg_properties = frozenset((
+ 'fill', 'fill-opacity', 'fill-rule',
+ 'stroke', 'stroke-width', 'stroke-linecap', 'stroke-linejoin',
+ 'stroke-opacity'))
+
+ acceptable_protocols = frozenset((
+ 'ed2k', 'ftp', 'http', 'https', 'irc',
+ 'mailto', 'news', 'gopher', 'nntp', 'telnet', 'webcal',
+ 'xmpp', 'callto', 'feed', 'urn', 'aim', 'rsync', 'tag',
+ 'ssh', 'sftp', 'rtsp', 'afs', 'data'))
+
+ acceptable_content_types = frozenset((
+ 'image/png', 'image/jpeg', 'image/gif', 'image/webp', 'image/bmp',
+ 'text/plain'))
# subclasses may define their own versions of these constants
- allowed_elements = acceptable_elements + mathml_elements + svg_elements
- allowed_attributes = acceptable_attributes + mathml_attributes + svg_attributes
+ allowed_elements = acceptable_elements | mathml_elements | svg_elements
+ allowed_attributes = acceptable_attributes | mathml_attributes | svg_attributes
allowed_css_properties = acceptable_css_properties
allowed_css_keywords = acceptable_css_keywords
allowed_svg_properties = acceptable_svg_properties
@@ -181,7 +197,7 @@ def sanitize_token(self, token):
# accommodate filters which use token_type differently
token_type = token["type"]
- if token_type in list(tokenTypes.keys()):
+ if token_type in tokenTypes:
token_type = tokenTypes[token_type]
if token_type in (tokenTypes["StartTag"], tokenTypes["EndTag"],
@@ -197,9 +213,8 @@ def sanitize_token(self, token):
def allowed_token(self, token, token_type):
if "data" in token:
- attrs = dict([(name, val) for name, val in
- token["data"][::-1]
- if name in self.allowed_attributes])
+ attrs = dict((name, val) for name, val in
+ token["data"][::-1] if name in self.allowed_attributes)
for attr in self.attr_val_is_uri:
if attr not in attrs:
continue
@@ -243,7 +258,7 @@ def disallowed_token(self, token, token_type):
if token.get("selfClosing"):
token["data"] = token["data"][:-1] + "/>"
- if token["type"] in list(tokenTypes.keys()):
+ if token["type"] in tokenTypes:
token["type"] = "Characters"
else:
token["type"] = tokenTypes["Characters"]
diff --git a/html5lib/tests/test_sanitizer.py b/html5lib/tests/test_sanitizer.py
index 0507d86b..82b72d0a 100644
--- a/html5lib/tests/test_sanitizer.py
+++ b/html5lib/tests/test_sanitizer.py
@@ -86,7 +86,8 @@ def test_sanitizer():
continue
attribute_value = 'foo'
if attribute_name in sanitizer.HTMLSanitizer.attr_val_is_uri:
- attribute_value = '%s://sub.domain.tld/path/object.ext' % sanitizer.HTMLSanitizer.allowed_protocols[0]
+ protocol = next(iter(sanitizer.HTMLSanitizer.allowed_protocols))
+ attribute_value = '%s://sub.domain.tld/path/object.ext' % protocol
yield (runSanitizerTest, "test_should_allow_%s_attribute" % attribute_name,
"foo <bad>bar</bad> baz
" % (attribute_name, attribute_value),
"foo bar baz
" % (attribute_name, attribute_value),